Panel : Cultural Heritage in the New Age of AI

Long title: Revealing Great Values of Diverse Cultural Heritage through Generating Smart Data in the New Age of AI
Starts at: Mon, Oct 21, 2024, 14:00 EDT
Finishes at: Mon, Oct 21, 2024, 15:30 EDT
Venue: Room A
Moderator: Sam Oh

The diversity of cultural heritage (CH) presents complexities in data processing. To meet the increasing demands for revealing their great values, smart data need to be generated for different information-bearing CH entities (which are usually non-textual and non-machine-readable) so that they can be identified, discovered, and used.
This panel will first bring in an analysis of the diverse CH entities in order to understand their complexity as well as the potentials and challenges in generating smart data for them in the new AI age.

Special cases in recent research projects in the world will be introduced. The CH entities rang from manuscripts, symbolic symbols, images, sound, smells, to museum specimens and other objects (Zeng).
Another perspective will bring the observation on various cultural entities in new domains, such as intangible cultural heritage, social events, and disasters (Sugimoto).
A special case for murals in one of the four famous Buddhist mountains will be given in detail (Xiao).
Due to their complex resource inauguration and other issues, the generating of (meta)data for those entities have been time-consuming and self-determining. The panel will then focus on the ongoing activities in the development of models, platforms, and services for CH.
The new efforts of establishing a core cultural model, especially for the digital archiving of intangible and experiential entities will be reported (Sugimoto).
The insights and lessons learned on developing over 20 in-use systems in over 20 years for publishing and studying CH data on the Semantic Web will be shared (Hyvönen).
The panelists will discuss together on the potentials and challenges in generating smart data to reveal the great values of diverse CH in the New Age of AI.

Moderator

Sam Oh

Sungkyunkwan University, Seoul, Korea
ORCID

LinkedIn
Sam Oh is a distinguished professor for global affairs at Sungkyunkwan University, Seoul, Korea, and an affiliate professor at University of Washington iSchool. HIS expertise spans data modeling, metadata design, and ontology design. With funded projects and consultancy for various companies and government sectors, he held leadership roles such as a chair of iSchools, had tenure chairing both TC46/SC9 (Identification & Description) and ISO/IEC JTC1 SC34 (Document Description and Processing Languages). He is the executive director of Dublin Core Metadata Initiative (DCMI), the ambassador of iSchools, and chairs TC46/SC4 (Technical Interoperability).

Presentations

Introduction: Recent research projects for generating smart data for diverse CH entities in the New Era of AI

Smart data means the trusted, contextualized, relevant, cognitive, predictive, and consumable data at any scale, revealing the most important V(value) of big data. A fundamental advancement of smart data that distinguishes it from other approaches is the methodology of big data, which assumes the ability to reveal the unknown-unknowns. The smart data concept is essential in relation to the role of libraries, archives, and museums (LAMs) in supporting Digital Humanities research.

In the new era of AI, smart data may be efficiently processed using AI technology while also being used by AI to generate intelligent applications and produce high-quality data. However, since information-bearing CH entities are usually non-textual and non-machine-readable, generating smart data for diverse CH resources presents complexities in data processing.

This introduction will bring some special cases in recent innovative research projects in the world, ranging from working on manuscripts, symbolic symbols, images, sound, smells, to museum specimens and other objects. Such advancement makes applications for promoting CH more abundant and practical.

Marcia Lei Zeng

Kent State University
ORCID

WebPage
Marcia Lei Zeng is a Professor of Information Science at Kent State University (USA). Her primary research interests include knowledge organization systems, linked data, metadata, smart data and big data, semantic technologies, and digital humanities. She has authored over 100 research papers and six books. Her research projects have received funding from the NSF, IMLS, OCLC, Fulbright, and other organizations. She has chaired and served on committees, working groups, and executive boards including IFLA, SLA, ASIS&T, NISO, ISO, DCMI, ISKO, iSchools, and W3C. Currently, she is chairing the DCMI Education Committee, while serving as a member of the DCMI Governing Board and ISKO Board of Directors.

Digital Humanities on the Semantic Web: Lessons Learned from Developing In-use Linked Open Data Services and Semantic Portals for Cultural Heritage

This presentation reviews lessons learned on developing over 20 in-use systems in over 20 years for publishing and studying Cultural Heritage data on the Semantic Web, including museum collections, bibliographical data and manuscripts, military history, biographies and narratives, epistolary data, archaeology, law, parliamentary data, and art. Targeted to Digital Humanities researchers, application developers, and the public, these systems include a Linked Open Data (LOD) service with a live SPARQL endpoint that can be used with modest programming skills, and a ready-to-
use semantic portal on top of it. This work has evolved gradually into the so-called Sampo Model for creating and publishing Knowledge Graphs (KG) as LOD services and semantic portal User Interfaces (UI).

Eero Hyvönen

Aalto University and University of Helsinki
ORCID

WebPage
Eero Hyvönen (https://seco.cs.aalto.fi/u/eahyvone/) is professor of semantic media technology at the Aalto University, Department of Computer Science, and director of Helsinki Centre for Digital Humanities (HELDIG) at the University of Helsinki. A major recent theme (since 2001) in his research has been the Semantic Web and linked (open) data technologies. He has been developing with his Semantic Computing Research Group (SeCo) (https://seco.cs.aalto.fi/) the national semantic web infrastructure in Finland (https://seco.cs.aalto.fi/projects/lodi4dh/) and its applications in different areas, such as Cultural Heritage and Digital Humanities (https://seco.cs.aalto.fi/applications/sampo/). Eero Hyvönen has published over 500 research articles and books and has got several international and national awards. He acts in the editorial boards of several international journals and has co-chaired and acted in the program committees of tens of major conferences.

The Role of metadata in the digital publishing of cultural heritage -- A special case of Shanxi cultural heritage studies

Shanxi is one of the provinces with the longest history and richest ancient cultural heritage in China. Mount Wutai, a mountainous area located in Shanxi, is one of the four famous Buddhist mountains in China. It was listed as a World Cultural Heritage by UNESCO in 2000. Mount Wutai has 108 ancient Buddhist temples, the earliest of which can be traced back to the wooden structure of Foguang Temple in the Tang Dynasty in the 9th century AD. These ancient buildings and their inscriptions, sculptures, and murals are all precious cultural heritage.
The murals of Mount Wutai cover a total area of more than 2,000 square meters and are distributed in more than 30 temples, including Buddhist teachings and classic literary stories. Using the digital publishing research project of Mount Wutai murals of the Shanxi Institute of Digital Humanities as a case study, this presentation will discuss the role of metadata in the construction of cultural heritage smart data. In particular, it introduces the data solution of the digital publishing project, including: (1) image data collection and digitizing of murals; (2) standard design, cataloging and linking of mural metadata; (3) segmentation and data association of mural image; (4) how metadata supports machine learning and automatic processing model training of image data, etc. The achievements of this project give full play to the role of metadata and provide a data solution for the construction of the Mount Wutai Mural Database of Shanxi Publishing and Media Group.
This presentation also outlines another ongoing research project, "GIS Application in the Study of Intangible Cultural Heritage in Shanxi".

Long XIAO

Peking University Library / Shanxi Institute of Digital Humanities and Digital Publishing
ORCID
Xiao Long, a professor of Peking University Library, a graduate tutor, concurrently serves as the information coordinator of IFLA Digital Humanities/Digital Scholarship SIG，and the director of the User Research and Service Section of the Academic Research Committee of the Library Society of China, Chief Expert of Shanxi Institute of Digital Humanities. She has published a large number of monographs, papers, online course, national standard on library management and user service, data and digital collection development, digital humanities and digital publishing，information resource sharing.

Metadata modeling based on the One-to-One Principle to digitally curate and archive intangible entities in the cultural and historical domains: data models to help identify the entities and the relationships among them for digital archiving

The scope of the digital archiving has drastically expanded to encompass various domains such as intangible cultural heritage, social events, natural and man-made disasters, and so on in the 21st century. This presentation will discuss data modeling to digitally curate and archive intangible entities in the cultural and historical domains. The One-to-One principle of Metadata is applied to the metadata modeling between the original objects (which may be intangible or ephemeral) / their surrogates and their metadata.

Shigeo Sugimoto

University of Tsukuba
ORCID
Shigeo Sugimoto received his BE, ME, and Ph.D. degrees from the Department of Information Science, Faculty of Engineering, Kyoto University in 1977, 1979, and 1985, respectively. Until March 2019, he was a full-time faculty member at the Faculty of Library, Information and Media Science, University of Tsukuba (formerly University of Library and Information Science), Japan. Sugimoto first participated in the 4th Dublin Core Workshop in 1997 and has been closely working with DCMI since then. Currently, he is a member of the Governing Board of DCMI. His research interests include metadata models for digital archives that collect intangible cultural and historical entities, such as intangible cultural heritage, cultural/historical events, and transient and dynamic objects.